© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117152
    Prev
    Next
    INDEX
    Explanations

    thousands of miles or years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ous
    -0.09
    oyer
    -0.08
    aji
    -0.08
     gearing
    -0.08
    gesch
    -0.08
     Bart
    -0.08
    abet
    -0.08
    asing
    -0.08
     Harvey
    -0.08
     pad
    -0.08
    POSITIVE LOGITS
    -plus
    0.13
    dpi
    0.11
    +
    0.11
    mAh
    0.11
    sat
    0.11
    MW
    0.10
    ths
    0.10
    -strong
    0.10
    ä¸ĩ
    0.10
    SW
    0.10
    Activations Density 0.158%

    No Known Activations